{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "e915e75c-62aa-4e6a-891a-66172319df52",
   "metadata": {},
   "source": [
    "# Step2: Simulation using TFdisc"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6cfb8ef6-ff98-4460-9ed0-e3c89bc4457e",
   "metadata": {},
   "source": [
    "Using the imputation data and gene regulatory networks obtained in the first step, transcription factor (TF) perturbation simulations can be performed. The main steps include:"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "953eac0c-9169-4666-915e-c0da2a560ec9",
   "metadata": {},
   "source": [
    "#### 1. Import library"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "6181f876-3564-481f-9a3d-2b6a24cb3d8f",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import pickle\n",
    "import TFdisc as tc\n",
    "import warnings\n",
    "warnings.filterwarnings(\"ignore\")\n",
    "import os"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "02e9bc33-522d-47d6-bad1-c4aa77889cdb",
   "metadata": {},
   "source": [
    "#### 2. Import data"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "8fa9a292-a024-49c4-ba09-9258aa4000d4",
   "metadata": {},
   "source": [
    "Here, we load the filtered transcription factor (TF) and highly variable gene lists,along with the imputation data and gene regulatory network."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "6b7b523c-7376-4934-8221-714ac4bd27bb",
   "metadata": {},
   "outputs": [],
   "source": [
    "TF_list = list(pd.read_csv(\"./data/TF_list.csv\",index_col=0).iloc[:,0])\n",
    "HVG_list = list(pd.read_csv(\"./data/HVG_list.csv\",index_col=0).iloc[:,0])\n",
    "ave_data = pd.read_csv(\"./data/ave_data.csv\",index_col=0)\n",
    "ave_data = ave_data.T\n",
    "with open(\"./data/alltop.pkl\", \"rb\") as tf:\n",
    "    grn_result = pickle.load(tf)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "69fdc4ed-e2b2-4b03-9582-f37f401fda96",
   "metadata": {},
   "source": [
    "#### 3. Build predictive models"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "fb7404ee-6c0a-4f6b-b960-7dd64667964f",
   "metadata": {},
   "source": [
    "Construct kernel ridge regression model for each gene."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "03c3368c-5f4b-439e-9c87-4460320aeaf5",
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Task Progress: 100%|███████████████████| 5644/5644 [2:51:37<00:00,  1.82s/items]"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "running time = 10297.27405333519\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    }
   ],
   "source": [
    "tc.train_model.TF_model(ave_data,list(set(TF_list) | set(HVG_list)),\n",
    "                     grn_result,save = None,method = \"krr\",verbose = True,\n",
    "                     test_size=0.1, model_score=False)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "dfd2e326-2a14-4042-91d5-50eda034ac12",
   "metadata": {},
   "source": [
    "Construct Random Forest Model for each gene."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "c15d3169-6d78-4d3b-a9b5-22677fed78c7",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Task Progress: 100%|███████████████████| 5644/5644 [8:32:07<00:00,  5.44s/items]"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "running time = 5.573473691940308\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    }
   ],
   "source": [
    "tc.train_model.TF_model(ave_data,list(set(TF_list) | set(HVG_list)),\n",
    "                     grn_result,save = None,method = \"rf\",verbose = True,\n",
    "                     test_size=0.1, model_score=False)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "60242425-4f26-46d8-9954-4132b59525f8",
   "metadata": {},
   "source": [
    "#### 4. In silico TF perturbation simulation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "181f8bd2-9bb9-4cbd-a879-cd069fb66fe6",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "pre_data = tc.gen_model.combine_predict(ave_data,TF_list,HVG_list,grn_result,\"./krr/\",rf_premodel=\"./rf/\",\n",
    "                    TF=\"Nkx2-1\",krr_time=5,rf_time=1,\n",
    "                    core=30,matrix_err = 10000,min_matrix_err = 0.01)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "id": "a25eb68c-fcce-42c0-8cf5-034e53a632cf",
   "metadata": {},
   "outputs": [],
   "source": [
    "pre_data.to_csv('./data/Nkx2_1_perturb.csv') "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "0003f5f1-9148-4b77-97b9-c252749d8611",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python [conda env:TFdisc]",
   "language": "python",
   "name": "conda-env-TFdisc-py"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.10.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}